论文部分内容阅读
目前储量的分类标准是通过划分指标值的范围来确定的,这就要求所有指标值恰好符合既定的指标范围,否则难以划分储量类别.为克服这一问题,结合模糊C均值算法和BP神经网络实现难采储量的分类.首先基于效益指标运用模糊C均值算法自动搜索储量的最佳类别,再利用BP神经网络建立储量效益指标类别与储量属性指标之间的关系表达式.在已知储量指标值的情况下,通过此关系式即可求得储量的类别.最后以大庆某油田为实例,对其难采储量进行了分类,有效指导难采储量滚动开发决策.
At present, the classification standard of reserves is determined by dividing the range of index values, which requires that all the index values coincide with the established index range, otherwise, it is difficult to classify the reserve categories.In order to overcome this problem, combining fuzzy C-means algorithm and BP neural network To realize the classification of hard-to-extract reserves.Firstly, based on the efficiency index, the fuzzy C-means algorithm is used to automatically search the best category of reserves, and then BP neural network is used to establish the relational expression between the categories of reserve benefit indicators and reserve attributes.After the known reserves index Value, we can get the type of reserve by this relation.Finally, taking Daqing Oilfield as an example, we classified its recoverable reserves and effectively guided the decision of rolling development of recoverable reserves.